Over decades, neuroscience has accumulated a wealth of research results ...
The advancements in vision-based tactile sensors have boosted the aptitu...
In vanilla federated learning (FL) such as FedAvg, the parameter server ...
Generating video stories from text prompts is a complex task. In additio...
Retrieval augmentation, which enhances downstream models by a knowledge
...
Over the past few decades, ubiquitous sensors and systems have been an
i...
Living needs refer to the various needs in human's daily lives for survi...
Since existing mobile communication networks may not be able to meet the...
We present ArrayBot, a distributed manipulation system consisting of a 1...
We study domain-adaptive image synthesis, the problem of teaching pretra...
Many fine-grained classification tasks, like rare animal identification,...
Deep spiking neural networks (SNNs) have drawn much attention in recent ...
Spiking neural networks (SNNs) offer a promising energy-efficient altern...
Traffic steering (TS) is a promising approach to support various service...
Surgical phase recognition (SPR) is a crucial element in the digital
tra...
Many applications can benefit from personalized image generation models,...
This paper proposes a method for generating images of customized objects...
Diffusion models have achieved remarkable success in text-to-image
gener...
Prototype, as a representation of class embeddings, has been explored to...
Principal Component Analysis (PCA) is a widely used technique in machine...
We propose Stratified Image Transformer(StraIT), a pure
non-autoregressi...
Recent work in news recommendation has demonstrated that recommenders ca...
This paper investigates a phenomenon where query-based object detectors
...
Achieving multiple genres and long-term choreography sequences from give...
Diffusion models, which learn to reverse a signal destruction process to...
The Multi-Objective Multi-Agent Path Finding (MO-MAPF) problem is the pr...
Generative modeling and representation learning are two key tasks in com...
Recent research has demonstrated the capability of behavior signals capt...
It is expensive to collect training data for every possible domain that ...
Medical image segmentation aims to automatically extract anatomical or
p...
To help improve the safety and accessibility of indoor spaces, researche...
We present Phenaki, a model capable of realistic video synthesis, given ...
Transferring knowledge from an image synthesis model trained on a large
...
While parameter efficient tuning (PET) methods have shown great potentia...
BERT-style models pre-trained on the general corpus (e.g., Wikipedia) an...
Recently, open radio access network (O-RAN) has become a promising techn...
We present the Pathways Autoregressive Text-to-Image (Parti) model, whic...
This paper studies faithful explanations for Graph Neural Networks (GNNs...
Multicasting is an efficient technique to simultaneously transmit common...
The rapid increase in the adoption of Internet-of-Things (IoT) devices r...
Dense retrievers encode texts and map them in an embedding space using
p...
In recent works, utilizing a deep network trained on meta-training set s...
Transformers have recently gained significant attention in the computer
...
To make full use of computer vision technology in stores, it is required...
We propose a test-time adaptation method for cross-domain image segmenta...
A major challenge in image segmentation is classifying object boundaries...
Product quantization (PQ) coupled with a space rotation, is widely used ...
Medical image segmentation, which aims to automatically extract anatomic...
With the success of down streaming task using English pre-trained langua...
Generative transformers have experienced rapid popularity growth in the
...